LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
hub
Scaling diffusion language models via adaptation from autoregressive models
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
verdicts
UNVERDICTED 11representative citing papers
ΔLPS is a gradient-guided discrete posterior sampler for inverse problems that works with masked or uniform discrete diffusion priors and outperforms prior discrete methods on image restoration tasks.
Pretrained language models are used as energy functions for Glauber dynamics in discrete text diffusion, improving generation quality over prior diffusion LMs and matching autoregressive models on benchmarks and reasoning tasks.
FoCore uses self-contrast on early-converging high-density tokens to boost diffusion LLM quality on reasoning benchmarks while cutting decoding steps by over 2x.
BARD bridges autoregressive and diffusion VLMs with progressive block merging plus stage-wise intra-diffusion distillation, delivering 3x speedup and new SOTA on open dVLMs using under 4.4M data points.
LangFlow is the first continuous diffusion language model to rival discrete diffusion on perplexity and generative perplexity while exceeding autoregressive baselines on several zero-shot tasks.
Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
In diffusion language models, coarse linguistic labels stabilize earlier than exact token identity, uncertainty tracks correctness, and mid-trajectory states are most sensitive to perturbations.
DLMs exhibit lower n-gram entropy, higher semantic coherence, and higher semantic diversity than ARMs, primarily due to bidirectional context and remasking decoding strategies.
AHD uses real-time stability monitoring with dynamic anchors to allow early cross-block decoding of converged tokens, cutting steps by up to 80% and raising performance on benchmarks like BBH.
citing papers explorer
-
Large Language Diffusion Models
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
-
Discrete Langevin-Inspired Posterior Sampling
ΔLPS is a gradient-guided discrete posterior sampler for inverse problems that works with masked or uniform discrete diffusion priors and outperforms prior discrete methods on image restoration tasks.
-
Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion
Pretrained language models are used as energy functions for Glauber dynamics in discrete text diffusion, improving generation quality over prior diffusion LMs and matching autoregressive models on benchmarks and reasoning tasks.
-
Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast
FoCore uses self-contrast on early-converging high-density tokens to boost diffusion LLM quality on reasoning benchmarks while cutting decoding steps by over 2x.
-
BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation
BARD bridges autoregressive and diffusion VLMs with progressive block merging plus stage-wise intra-diffusion distillation, delivering 3x speedup and new SOTA on open dVLMs using under 4.4M data points.
-
LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
LangFlow is the first continuous diffusion language model to rival discrete diffusion on perplexity and generative perplexity while exceeding autoregressive baselines on several zero-shot tasks.
-
Coupling Models for One-Step Discrete Generation
Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
-
Measuring Temporal Linguistic Emergence in Diffusion Language Models
In diffusion language models, coarse linguistic labels stabilize earlier than exact token identity, uncertainty tracks correctness, and mid-trajectory states are most sensitive to perturbations.
-
Differences in Text Generated by Diffusion and Autoregressive Language Models
DLMs exhibit lower n-gram entropy, higher semantic coherence, and higher semantic diversity than ARMs, primarily due to bidirectional context and remasking decoding strategies.
-
Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models
AHD uses real-time stability monitoring with dynamic anchors to allow early cross-block decoding of converged tokens, cutting steps by up to 80% and raising performance on benchmarks like BBH.